datatable.models.Ftrl.model

Trained models weights, i.e. z and n coefficients in per-coordinate FTRL-Proximal algorithm.

Parameters

return
Frame

A frame of shape (nbins, 2 * nlabels), where nlabels is the total number of labels the model was trained on, and nbins is the number of bins used for the hashing trick. Odd and even columns represent the z and n model coefficients, respectively.